Sweeper Scheduling Method, Device, Computer Equipment and Storage Medium

Abstract

This application relates to a sweeper scheduling method, device, computer device, storage medium, and computer program product. The method includes: obtaining images captured by each binocular camera; determining whether the area corresponding to each image is an area to be cleaned according to each image; determining the cleaning task volume of each sweeper in the target area according to the image corresponding to each area to be cleaned; determining the target cleaning area of each sweeper according to the cleaning task volume of each sweeper; and determining the cleaning path of each sweeper according to the map information of the target area and the target cleaning area of each sweeper, and sending it to the corresponding sweeper. Thereby, it can ensure that the real-time sanitation status of the target area is good. Compared with scheduling sweepers for cleaning at fixed times, the scheduling method of this application is more reasonable and comprehensive. Thus, the cleaning efficiency is improved, and the utilization of sweeper resources is maximized.

Description

Technical Field

[0001] The present application relates to the technical field of sweeper scheduling, and particularly to a sweeper scheduling method, device, computer device, storage medium, and computer program product. Background Art

[0002] Currently, the scheduling methods for park sweepers are generally relatively simple. The sweepers perform cleaning work on the entire park at fixed times. This scheduling method does not consider the real-time sanitation conditions of the park, is unreasonable and incomplete, has low cleaning efficiency, unsatisfactory results, and cannot maximize the utilization of sweeper resources. Summary of the Invention

[0003] Based on this, in view of the above technical problems, it is necessary to provide a sweeper scheduling method, device, computer device, computer-readable storage medium, and computer program product that can reasonably and comprehensively schedule sweepers, have high cleaning efficiency, and maximize the utilization of sweeper resources.

[0004] In a first aspect, the present application provides a sweeper scheduling method. The method includes:

[0005] Obtain the images captured by each binocular camera;

[0006] According to each image, determine whether the area corresponding to each image is an area to be cleaned;

[0007] According to the image corresponding to each area to be cleaned, determine the cleaning task volume of each sweeper in the target area;

[0008] According to the cleaning task volume of each sweeper, determine the target cleaning area of each sweeper;

[0009] According to the map information of the target area and the target cleaning area of each sweeper, determine the cleaning path of each sweeper and send it to the corresponding sweeper.

[0010] In one embodiment,

[0011] According to each image, determining whether the area corresponding to each image is an area to be cleaned includes:

[0012] Input each image into a first preset model and output the amount of garbage corresponding to each image;

[0013] Determine whether the amount of garbage corresponding to each image is greater than a preset threshold, and list the area corresponding to the image with the amount of garbage greater than the preset threshold as an area to be cleaned.

[0014] In one embodiment, according to the cleaning task volume of each sweeper, determining the target cleaning area of each sweeper includes:

[0015] Take any cleaning area corresponding to an image in all areas to be cleaned as the initial area;

[0016] For any cleaning vehicle, determine whether the cleaning task amount corresponding to the initial area is within a preset range; the preset range is determined according to the cleaning task amount of any cleaning vehicle; if it is, take the initial area as the target cleaning area of any cleaning vehicle;

[0017] If not, determine the set of target cleaning areas of any cleaning vehicle, and the target cleaning set includes the initial area; repeatedly select the nearest area to be cleaned based on the set of target cleaning areas and add it to the set of target cleaning areas until the total cleaning task amount corresponding to the set of target cleaning areas is within the preset range, take the areas to be cleaned in the set of target cleaning areas as the target cleaning areas of any cleaning vehicle, and delete the target cleaning areas of any cleaning vehicle from all areas to be cleaned.

[0018] In one embodiment, according to the map information of the target area and the target cleaning areas of each cleaning vehicle, determine the cleaning path of each cleaning vehicle, including:

[0019] For any cleaning vehicle, determine the current position of any cleaning vehicle and use it as the cleaning starting point; determine the positions of each target garbage included in the target cleaning area of any cleaning vehicle;

[0020] Take the position of the target garbage with the farthest distance from any cleaning vehicle as the cleaning end point of any cleaning vehicle, take the positions of the remaining target garbage as cleaning points, and take the intersections in the map information as gathering points;

[0021] Traverse the cleaning starting point, gathering points, cleaning points and cleaning end point, obtain all paths for any cleaning vehicle to reach the cleaning end point from the cleaning starting point, and take the path with the shortest distance among all paths as the cleaning path of any cleaning vehicle.

[0022] In one embodiment, the method further includes:

[0023] According to the cleaning path of each cleaning vehicle, correspondingly generate the driving control signal of each cleaning vehicle, and send the driving control signal of each cleaning vehicle to the corresponding cleaning vehicle, and the driving control signal is used to instruct the cleaning vehicle to reach the target cleaning area and clean the garbage.

[0024] In one embodiment, the method further includes:

[0025] Obtain the current images captured by each binocular camera at the current moment;

[0026] Based on each current image, determine whether there is still garbage in each target cleaning area; if there is, determine the cleaning path of the target cleaning vehicle according to the map information of the target area and the target cleaning area with garbage, and send it to the corresponding target cleaning vehicle.

[0027] In a second aspect, the present application also provides a cleaning vehicle scheduling device. The device includes:

[0028] A first acquisition module, configured to acquire images captured by each binocular camera;

[0029] A first determination module, configured to determine, according to each image, whether the area corresponding to each image is an area to be cleaned;

[0030] A second determination module, configured to determine the cleaning task amount of each cleaning vehicle in the target area according to the image corresponding to each area to be cleaned;

[0031] A third determination module, configured to determine the target cleaning area of each cleaning vehicle according to the cleaning task amount of each cleaning vehicle;

[0032] A fourth determination module, configured to determine the cleaning path of each cleaning vehicle according to the map information of the target area and the target cleaning area of each cleaning vehicle, and send it to the corresponding cleaning vehicle.

[0033] In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0034] Acquire images captured by each binocular camera;

[0035] According to each image, determine whether the area corresponding to each image is an area to be cleaned;

[0036] According to the image corresponding to each area to be cleaned, determine the cleaning task amount of each cleaning vehicle in the target area;

[0037] According to the cleaning task amount of each cleaning vehicle, determine the target cleaning area of each cleaning vehicle;

[0038] According to the map information of the target area and the target cleaning area of each cleaning vehicle, determine the cleaning path of each cleaning vehicle, and send it to the corresponding cleaning vehicle.

[0039] In a fourth aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0040] Acquire images captured by each binocular camera;

[0041] Based on each image, determine whether the area corresponding to each image is an area to be cleaned;

[0042] Based on the image corresponding to each area to be cleaned, determine the cleaning task amount of each cleaning vehicle in the target area;

[0043] Based on the cleaning task amount of each cleaning vehicle, determine the target cleaning area of each cleaning vehicle;

[0044] Based on the map information of the target area and the target cleaning area of each cleaning vehicle, determine the cleaning path of each cleaning vehicle and send it to the corresponding cleaning vehicle.

[0045] In a fifth aspect, the present application also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0046] Obtain the images captured by each binocular camera;

[0047] Based on each image, determine whether the area corresponding to each image is an area to be cleaned;

[0048] Based on the image corresponding to each area to be cleaned, determine the cleaning task amount of each cleaning vehicle in the target area;

[0049] Based on the cleaning task amount of each cleaning vehicle, determine the target cleaning area of each cleaning vehicle;

[0050] Based on the map information of the target area and the target cleaning area of each cleaning vehicle, determine the cleaning path of each cleaning vehicle and send it to the corresponding cleaning vehicle.

[0051] The above-mentioned sweeper scheduling method, device, computer equipment, storage medium, and computer program product obtain the images captured by each binocular camera; determine whether the area corresponding to each image is an area to be cleaned according to each image; determine the cleaning task volume of each sweeper in the target area according to the image corresponding to each area to be cleaned; determine the target cleaning area of each sweeper according to the cleaning task volume of each sweeper; determine the cleaning path of each sweeper according to the map information of the target area and the target cleaning area of each sweeper, and send it to the corresponding sweeper. Since the cleaning situation of the target area is monitored in real time, when there is garbage in the target area, the sweeper is instructed to clean the area where the garbage exists, so that the real-time sanitation status of the target area can be ensured to be good. Compared with scheduling the sweeper to clean at a fixed time, the scheduling method of this application is more reasonable and comprehensive. Furthermore, since when there is garbage in the target area, all the sweepers in the target area are scheduled to clean, and the cleaning task volume of each sweeper is not much different, the cleaning efficiency is improved, and the sweeper resources are utilized to the maximum extent. In addition, after determining the target cleaning area of each sweeper, the cleaning path is planned for each sweeper, so that each sweeper can reach the target cleaning area faster, thereby improving the cleaning efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a schematic flowchart of the sweeper scheduling method in an embodiment;

[0053] Figure 2 It is a structural block diagram of the sweeper scheduling device in an embodiment;

[0054] Figure 3 It is an internal structure diagram of the computer equipment in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0055] In order to make the objectives, technical solutions, and advantages of this application clearer, the following further details this application in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit this application.

[0056] Currently, the scheduling method of park sweepers is generally relatively simple. The sweepers clean the entire park at fixed times; this scheduling method does not consider the real-time sanitation status of the park, is unreasonable and incomplete, has low cleaning efficiency, unsatisfactory results, and cannot utilize the sweeper resources to the maximum extent.

[0057] It can be understood that the terms "first", "second", etc. used in this application can be used herein to describe various technical terms. Unless otherwise specified, these technical terms are not limited by these terms. These terms are only used to distinguish one technical term from another. For example, without departing from the scope of this application, the first determination module and the second determination module can be the same or different.

[0058] In view of the problems existing in the above related technologies, an embodiment of the present invention provides a cleaning vehicle scheduling method. This method can be applied to a server, or to a terminal, or to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the server can be implemented by an independent server or a server cluster composed of multiple servers. The terminal can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. It should be noted that the quantity referred to by "multiple" and the like mentioned in each embodiment of this application all refer to the quantity of "at least two". For example, "multiple" means "at least two".

[0059] In one embodiment, as Figure 1 shown, a cleaning vehicle scheduling method is provided. In this method, a plurality of binocular cameras are set in the target area. This embodiment takes the application of this method to a server as an example. Among them, the server can include an intelligent scheduling platform. Specifically, the intelligent scheduling platform executes this method. This method includes the following steps:

[0060] 102. Obtain the images captured by each binocular camera.

[0061] It should be noted that the target area can be a park or a community with cleaning vehicles. The embodiments of this application do not make specific limitations on this. It should also be noted that the camera is not necessarily limited to a binocular camera, as long as it is a camera with a ranging function. It can be understood that if the target area is a park, the area cleaned by the cleaning vehicle is mainly the road surface in the park. Then, the plurality of binocular cameras set in the target area are used to capture the road surface in the park and feed the captured images back to the server. The server obtains the cleaning condition of the road surface through the images.

[0062] 104. Determine whether the area corresponding to each image is an area to be cleaned according to each image.

[0063] Specifically, the number of garbage corresponding to each image can be determined through a deep learning object detection algorithm; it is determined whether the number of garbage corresponding to each image is greater than a preset threshold, and the area corresponding to the image with the number of garbage greater than the preset threshold is listed as the area to be cleaned.

[0064] 106. According to the image corresponding to each area to be cleaned, determine the cleaning task amount of each cleaning vehicle in the target area.

[0065] Specifically, according to the image corresponding to each area to be cleaned, the cleaning task amount corresponding to each area to be cleaned can be determined; the cleaning task amount corresponding to each area to be cleaned includes the required time for cleaning each area to be cleaned; according to the cleaning task amount corresponding to each area to be cleaned, determine the total cleaning task amount corresponding to all areas to be cleaned; according to the total cleaning task amount corresponding to all areas to be cleaned, determine the cleaning task amount of each cleaning vehicle.

[0066] Specifically, according to the image corresponding to each area to be cleaned, determining the cleaning task amount corresponding to each area to be cleaned includes but is not limited to: inputting the image corresponding to each area to be cleaned into a second preset model, outputting the number and type of garbage contained in the image corresponding to each area to be cleaned, and according to the number and type of garbage contained in the image corresponding to each area to be cleaned, determine the cleaning task amount corresponding to each area to be cleaned. Since the cleaning task amount is quantified by time, it can be understood that the more the number of garbage contained in each area to be cleaned, correspondingly, the higher the cleaning task amount corresponding to each area to be cleaned. At the same time, it can also be understood that the type of garbage will also affect the cleaning task amount. For example, for leaves and water bottles, the required time for the cleaning vehicle to clean the water bottle is longer than that of the leaves.

[0067] It should be noted that the cleaning task amount of each cleaning vehicle can be a range or a specific value, and the embodiments of the present application do not limit this. Specifically, if it is a specific value, the cleaning task amount of each cleaning vehicle can be determined through the following steps: determine the number of cleaning vehicles in the target area, obtain the ratio between the total cleaning task amount corresponding to all areas to be cleaned and the number of cleaning vehicles, and use the ratio as the cleaning task amount of each cleaning vehicle. If it is a range, after obtaining the ratio between the total cleaning task amount corresponding to all areas to be cleaned and the number of cleaning vehicles, determine a range according to the ratio, and use the range as the cleaning task amount of each cleaning vehicle.

[0068] 108. According to the cleaning task amount of each cleaning vehicle, determine the target cleaning area of each cleaning vehicle.

[0069] 110. According to the map information of the target area and the target cleaning area of each cleaning vehicle, determine the cleaning path of each cleaning vehicle and send it to the corresponding cleaning vehicle.

[0070] It should be noted that after determining the cleaning path of each sweeper and sending it to the corresponding sweeper, each sweeper performs cleaning according to the corresponding cleaning path.

[0071] In the above sweeper scheduling method, images captured by each binocular camera are obtained; according to each image, it is determined whether the area corresponding to each image is an area to be cleaned; according to the images corresponding to each area to be cleaned, the cleaning task amount of each sweeper in the target area is determined; according to the cleaning task amount of each sweeper, the target cleaning area of each sweeper is determined; according to the map information of the target area and the target cleaning area of each sweeper, the cleaning path of each sweeper is determined and sent to the corresponding sweeper. Since the cleaning situation of the target area is monitored in real time, when there is garbage in the target area, the sweeper is instructed to clean the area where the garbage exists, so that the real-time sanitation status of the target area can be ensured to be good. Compared with scheduling the sweeper to clean at a fixed time, the scheduling method of this application is more reasonable and comprehensive. Moreover, since when there is garbage in the target area, all the sweepers in the target area are scheduled to clean, and the cleaning task amounts of each sweeper are not much different, the cleaning efficiency is improved, and the utilization of sweeper resources is maximized. In addition, after determining the target cleaning area of each sweeper, the cleaning path is planned for each sweeper, so that each sweeper can reach the target cleaning area faster, thereby improving the cleaning efficiency.

[0072] In one embodiment, determining whether the area corresponding to each image is an area to be cleaned according to each image includes:

[0073] Each image is input into a first preset model, and the number of garbage corresponding to each image is output.

[0074] Among them, the first preset model can adopt the YOLOv5 model. It can be understood that in order to make the results output by the first preset model more accurate, before inputting each image into the first preset model, problems such as insufficient training samples can be solved through data fusion, training sample expansion, and transfer learning. Specifically, a large number of sample images obtained by photographing the target area and other areas similar to the target area can be obtained, and the pre-trained model is trained based on the sample images to obtain the first preset model.

[0075] Determine whether the number of garbage corresponding to each image is greater than a preset threshold, and list the areas corresponding to the images with the number of garbage greater than the preset threshold as areas to be cleaned.

[0076] It can be understood that the preset threshold can be determined according to the needs of the target area manager. For example, if the target area is a park and the park manager hopes that the park always maintains a high level of sanitation, correspondingly, the preset threshold can be set lower, such as setting the preset threshold to 10. If the park manager has no high requirements for the sanitation situation, correspondingly, the preset threshold can be set higher, such as setting the preset threshold to 50. It can be understood that the higher the preset threshold, the greater the cleaning task volume for each cleaning by the sweeper, and the lower the preset threshold, the smaller the cleaning task volume of the sweeper, which can ensure that the sanitation situation of the target area is always maintained at a high level.

[0077] In this embodiment, by inputting each image into the first preset model, the garbage quantity corresponding to each image is output; it is determined whether the garbage quantity corresponding to each image is greater than the preset threshold, and the area corresponding to the image with the garbage quantity greater than the preset threshold is listed as the area to be cleaned. Since the first preset model is obtained through training, the garbage quantity corresponding to each output image is more accurate.

[0078] In one embodiment, according to the cleaning task volume of each sweeper, the target cleaning area of each sweeper is determined, including:

[0079] Take the area to be cleaned corresponding to any image in all the areas to be cleaned as the initial area.

[0080] For any sweeper, judge whether the cleaning task volume corresponding to the initial area is within the preset range; the preset range is determined according to the cleaning task volume of any sweeper; if it is, take the initial area as the target cleaning area of any sweeper.

[0081] It should be noted that the process of determining the cleaning task volume corresponding to each area to be cleaned can refer to the process of the above embodiment "determine the cleaning task volume corresponding to each area to be cleaned according to the image corresponding to each area to be cleaned", which will not be elaborated here.

[0082] If not, determine the target cleaning area set of any sweeper, and the target cleaning set includes the initial area; based on the target cleaning area set, repeatedly select the area to be cleaned with the closest distance and add it to the target cleaning area set until the total cleaning task volume corresponding to the target cleaning area set is within the preset range, take the areas to be cleaned in the target cleaning area set as the target cleaning area of any sweeper, and delete the target cleaning area of any sweeper from all the areas to be cleaned.

[0083] Specifically, the nearest cleaning area to be cleaned can be repeatedly selected based on the set of target cleaning areas and added to the set of target cleaning areas. That is, each time a cleaning area to be cleaned is added to the set of target cleaning areas. It can be understood that the set of target cleaning areas may contain multiple target cleaning areas, and multiple cleaning areas to be cleaned that are the nearest can also be repeatedly selected based on the set of target cleaning areas and added to the set of target cleaning areas.

[0084] In this embodiment, any cleaning area corresponding to an image among all the cleaning areas to be cleaned is used as the initial area; for any cleaning vehicle, it is determined whether the cleaning task amount corresponding to the initial area is within a preset range; the preset range is determined according to the cleaning task amount of any cleaning vehicle; if it is, the initial area is used as the target cleaning area of any cleaning vehicle; if not, the set of target cleaning areas of any cleaning vehicle is determined, and the target cleaning set includes the initial area; the nearest cleaning area to be cleaned is repeatedly selected based on the set of target cleaning areas and added to the set of target cleaning areas until the total cleaning task amount corresponding to the set of target cleaning areas is within the preset range, and the cleaning areas to be cleaned in the set of target cleaning areas are used as the target cleaning areas of any cleaning vehicle, and the target cleaning areas of any cleaning vehicle are deleted from all the cleaning areas to be cleaned. Thus, it is ensured that the target cleaning areas of each cleaning vehicle are relatively concentrated, and the cleaning efficiency is improved accordingly.

[0085] In one embodiment, according to the map information of the target area and the target cleaning areas of each cleaning vehicle, the cleaning path of each cleaning vehicle is determined, including:

[0086] For any cleaning vehicle, the current position of any cleaning vehicle is determined and used as the cleaning starting point; the positions of each target garbage included in the target cleaning area of any cleaning vehicle are determined.

[0087] It can be understood that since the camera used is a binocular camera with a ranging function, the positions of each garbage included in the area corresponding to the image can be determined according to the image captured by the binocular camera.

[0088] The position of the target garbage that is the farthest from any cleaning vehicle is used as the cleaning end point of any cleaning vehicle, the positions of the remaining target garbage are all used as cleaning points, and the intersections in the map information are used as gathering points.

[0089] Traverse the cleaning starting point, gathering points, cleaning points and cleaning end point, obtain all the paths for any cleaning vehicle to reach the cleaning end point from the cleaning starting point, and use the path with the shortest distance among all the paths as the cleaning path of any cleaning vehicle.

[0090] In this embodiment, since the determined cleaning path of each cleaning vehicle is the path with the shortest distance, the cleaning efficiency of each cleaning vehicle can be improved.

[0091] In one embodiment, according to the cleaning path of each street sweeper, a driving control signal for each street sweeper is generated correspondingly, and the driving control signal for each street sweeper is sent to the corresponding street sweeper. The driving control signal is used to instruct the street sweeper to reach the target cleaning area and clean the garbage.

[0092] It should be noted that the street sweeper in the target area can be an intelligent street sweeper. The street sweeper can be equipped with a communication module, a GPS positioning module and an electronic control unit for real-time communication with the server. The communication module receives the cleaning path, garbage position information and driving control signal sent by the server. The electronic control unit receives the cleaning path, garbage position information and driving control signal sent by the communication module, controls the street sweeper to drive according to the cleaning path, and the GPS positioning module judges whether the street sweeper reaches the garbage position, and then cleans when it reaches the garbage position.

[0093] In this embodiment, by generating a driving control signal for each street sweeper according to the cleaning path of each street sweeper and sending the driving control signal for each street sweeper to the corresponding street sweeper, the driving control signal is used to instruct the street sweeper to reach the target cleaning area and clean the garbage. On the one hand, it helps the street sweeper quickly reach the target cleaning area, thereby improving the cleaning efficiency. On the other hand, it enables the street sweeper to perform automatic cleaning work according to the cleaning path, making it more intelligent.

[0094] In one embodiment, the current images captured by each binocular camera at the current moment are obtained; according to each current image, it is judged whether there is still garbage in each target cleaning area; if so, according to the map information of the target area and the target cleaning area where there is garbage, the cleaning path of the target street sweeper is determined and sent to the corresponding target street sweeper.

[0095] Specifically, each current image is input into a third preset model to output the garbage quantity corresponding to each target cleaning area. For any target cleaning area, it is judged whether the garbage quantity corresponding to any target cleaning area is greater than 0. If so, it is determined that there is still garbage in any target cleaning area. If not, it is determined that there is no garbage in any target cleaning area.

[0096] It should be noted that the target cleaning vehicle is the cleaning vehicle corresponding to the target cleaning area with garbage. In addition, the process of determining the cleaning path of the target cleaning vehicle can refer to the process of "determining the cleaning path of each cleaning vehicle according to the map information of the target area and the target cleaning area of each cleaning vehicle", which will not be elaborated here. After sending the cleaning path of the target cleaning vehicle to the corresponding target cleaning vehicle, it may further include: generating a driving control signal for the target cleaning vehicle according to the cleaning path of the target cleaning vehicle, and sending the driving control signal of the target cleaning vehicle to the corresponding target cleaning vehicle. The driving control signal is used to instruct the target cleaning vehicle to reach the target cleaning area with garbage and clean the garbage.

[0097] In this embodiment, by acquiring the current images captured by each binocular camera at the current moment; judging whether there is still garbage in each target cleaning area according to each current image; if so, determining the cleaning path of the target cleaning vehicle according to the map information of the target area and the target cleaning area with garbage, and sending it to the corresponding target cleaning vehicle. Since each target cleaning area is monitored in real time to detect the cleaning condition of the target cleaning area after each cleaning vehicle has cleaned, when there is still garbage in the target cleaning area of any cleaning vehicle, instructing any cleaning vehicle to clean the target cleaning area with remaining garbage again until it is detected that there is no garbage in the target cleaning area of any cleaning vehicle. Thus, the cleaning efficiency is improved.

[0098] In one embodiment, after determining the cleaning path of the target cleaning vehicle according to the map information of the target area and the target cleaning area with garbage, it further includes:

[0099] Determining the amount of garbage in the target cleaning area with garbage according to the current image corresponding to the target cleaning area with garbage; generating a vehicle speed control signal for the target cleaning vehicle according to the amount of garbage in the target cleaning area with garbage, and sending the vehicle speed control signal to the target cleaning vehicle.

[0100] Among them, the process of determining the amount of garbage in the target cleaning area with garbage can refer to the process of determining the amount of garbage in the process of determining whether the area corresponding to each image is the area to be cleaned according to each image, which will not be elaborated here.

[0101] It can be understood that the amount of garbage is negatively correlated with the vehicle speed of the target cleaning vehicle. The more the amount of garbage, the smaller the vehicle speed of the target cleaning vehicle accordingly, thereby improving the cleaning effect of the cleaning vehicle.

[0102] In this embodiment, determining the amount of garbage in the target cleaning area with garbage according to the current image corresponding to the target cleaning area with garbage; generating a vehicle speed control signal for the target cleaning vehicle according to the amount of garbage in the target cleaning area with garbage, and sending the vehicle speed control signal to the target cleaning vehicle. Thus, the cleaning effect of the cleaning vehicle is improved.

[0103] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the indications of the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least some of the steps or stages in other steps or other steps.

[0104] Based on the same inventive concept, an embodiment of the present application further provides a sweeper scheduling device for implementing the above-mentioned sweeper scheduling method. The solution provided by this device for solving problems is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the sweeper scheduling device provided below can refer to the limitations on the sweeper scheduling method in the above text, and will not be repeated here.

[0105] In one embodiment, as Figure 2 shown, a sweeper scheduling device is provided, including: a first acquisition module 202, a first determination module 204, a second determination module 206, a third determination module 208, and a fourth determination module 210, where:

[0106] The first acquisition module 202 is configured to acquire images captured by each binocular camera;

[0107] The first determination module 204 is configured to determine whether the area corresponding to each image is an area to be cleaned according to each image;

[0108] The second determination module 206 is configured to determine the cleaning task amount of each sweeper in the target area according to the image corresponding to each area to be cleaned;

[0109] The third determination module 208 is configured to determine the target cleaning area of each sweeper according to the cleaning task amount of each sweeper;

[0110] The fourth determination module 210 is configured to determine the cleaning path of each sweeper according to the map information of the target area and the target cleaning area of each sweeper, and send it to the corresponding sweeper.

[0111] In one embodiment, the first determination module 204 includes:

[0112] An output unit, configured to input each image into a first preset model and output the amount of garbage corresponding to each image;

[0113] A first determination unit, configured to determine whether the amount of garbage corresponding to each image is greater than a preset threshold, and list the area corresponding to the image with the amount of garbage greater than the preset threshold as an area to be cleaned.

[0114] In one embodiment, the third determination module 208 includes:

[0115] A first acting unit, configured to use the area to be cleaned corresponding to any one image in all areas to be cleaned as an initial area;

[0116] A judgment unit, configured to, for any cleaning vehicle, judge whether the cleaning task amount corresponding to the initial area is within a preset range; the preset range is determined according to the cleaning task amount of any cleaning vehicle; if so, use the initial area as the target cleaning area of any cleaning vehicle;

[0117] A second determination unit, configured to, if not, determine a set of target cleaning areas of any cleaning vehicle, where the target cleaning set includes the initial area; repeatedly select the nearest area to be cleaned based on the set of target cleaning areas and add it to the set of target cleaning areas until the total cleaning task amount corresponding to the set of target cleaning areas is within the preset range, use the areas to be cleaned in the set of target cleaning areas as the target cleaning areas of any cleaning vehicle, and delete the target cleaning areas of any cleaning vehicle from all areas to be cleaned.

[0118] In one embodiment, the fourth determination module 210 includes:

[0119] A third determination unit, configured to, for any cleaning vehicle, determine the current position of any cleaning vehicle and use it as a cleaning starting point; determine the positions of each target garbage included in the target cleaning area of any cleaning vehicle;

[0120] A second acting unit, configured to use the position of the target garbage farthest from any cleaning vehicle as the cleaning end point of any cleaning vehicle, use the positions of the remaining target garbage as cleaning points, and use the intersection in the map information as a gathering point;

[0121] An acquisition unit, configured to traverse the cleaning starting point, the gathering point, the cleaning points, and the cleaning end point, acquire all paths for any cleaning vehicle to reach the cleaning end point from the cleaning starting point, and use the path with the shortest distance among all paths as the cleaning path of any cleaning vehicle.

[0122] In one embodiment, the device further includes: a generation module configured to generate a driving control signal for each street sweeper according to the cleaning path of each street sweeper, and send the driving control signal of each street sweeper to the corresponding street sweeper. The driving control signal is used to instruct the street sweeper to reach the target cleaning area and clean the garbage.

[0123] In one embodiment, the device further includes:

[0124] a second acquisition module configured to acquire the current image captured by each binocular camera at the current moment;

[0125] a judgment module configured to judge whether there is still garbage in each target cleaning area according to each current image; if so, determine the cleaning path of the target street sweeper according to the map information of the target area and the target cleaning area where there is garbage, and send it to the corresponding target street sweeper.

[0126] Each module in the above street sweeper scheduling device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0127] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 3 shown. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as images captured by each binocular camera, map information of the target area, and cleaning paths of each street sweeper. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a street sweeper scheduling method.

[0128] Those skilled in the art can understand that Figure 3 the structure shown in

[0129] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0130] Obtain the images captured by each binocular camera;

[0131] According to each image, determine whether the area corresponding to each image is an area to be cleaned;

[0132] According to the images corresponding to each area to be cleaned, determine the cleaning task amount of each cleaning vehicle in the target area;

[0133] According to the cleaning task amount of each cleaning vehicle, determine the target cleaning area of each cleaning vehicle;

[0134] According to the map information of the target area and the target cleaning area of each cleaning vehicle, determine the cleaning path of each cleaning vehicle and send it to the corresponding cleaning vehicle.

[0135] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0136] Input each image into a first preset model and output the number of garbage corresponding to each image;

[0137] Determine whether the number of garbage corresponding to each image is greater than a preset threshold, and list the area corresponding to the image with the number of garbage greater than the preset threshold as an area to be cleaned.

[0138] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0139] Take the area to be cleaned corresponding to any image in all areas to be cleaned as the initial area;

[0140] For any cleaning vehicle, determine whether the cleaning task amount corresponding to the initial area is within a preset range; the preset range is determined according to the cleaning task amount of any cleaning vehicle; if so, take the initial area as the target cleaning area of any cleaning vehicle;

[0141] If not, determine the set of target cleaning areas of any cleaning vehicle, and the target cleaning set includes the initial area; based on the set of target cleaning areas, repeatedly select the nearest area to be cleaned and add it to the set of target cleaning areas until the total cleaning task amount corresponding to the set of target cleaning areas is within the preset range, take the areas to be cleaned in the set of target cleaning areas as the target cleaning areas of any cleaning vehicle, and delete the target cleaning areas of any cleaning vehicle from all areas to be cleaned.

[0142] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0143] For any street sweeper, determine the current position of any street sweeper as the cleaning starting point; determine the positions of each target piece of garbage included in the target cleaning area of any street sweeper.

[0144] Take the position of the target piece of garbage that is farthest from any street sweeper as the cleaning end point of any street sweeper, take the positions of the remaining target pieces of garbage as cleaning points, and take the intersections in the map information as gathering points.

[0145] Traverse the cleaning starting point, gathering points, cleaning points, and cleaning end point to obtain all paths for any street sweeper to reach the cleaning end point from the cleaning starting point, and take the path with the shortest distance among all paths as the cleaning path of any street sweeper.

[0146] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0147] According to the cleaning path of each street sweeper, correspondingly generate the driving control signal of each street sweeper, and send the driving control signal of each street sweeper to the corresponding street sweeper. The driving control signal is used to instruct the street sweeper to reach the target cleaning area and clean the garbage.

[0148] In one embodiment, when the processor executes the computer program, the following steps are further implemented: Obtain the current images captured by each binocular camera at the current moment; according to each current image, determine whether there is still garbage in each target cleaning area; if so, determine the cleaning path of the target street sweeper according to the map information of the target area and the target cleaning area where there is garbage, and send it to the corresponding target street sweeper.

[0149] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0150] Obtain the images captured by each binocular camera;

[0151] According to each image, determine whether the area corresponding to each image is an area to be cleaned;

[0152] According to the image corresponding to each area to be cleaned, determine the cleaning task amount of each street sweeper in the target area;

[0153] According to the cleaning task amount of each street sweeper, determine the target cleaning area of each street sweeper;

[0154] According to the map information of the target area and the target cleaning area of each street sweeper, determine the cleaning path of each street sweeper, and send it to the corresponding street sweeper.

[0155] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0156] Input each image into a first preset model to output the amount of garbage corresponding to each image;

[0157] Determine whether the amount of garbage corresponding to each image is greater than a preset threshold, and list the areas corresponding to the images with the amount of garbage greater than the preset threshold as areas to be cleaned.

[0158] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0159] Take the area to be cleaned corresponding to any one of the images in all the areas to be cleaned as the initial area;

[0160] For any cleaning vehicle, determine whether the cleaning task amount corresponding to the initial area is within a preset range; the preset range is determined according to the cleaning task amount of any cleaning vehicle; if it is, take the initial area as the target cleaning area of any cleaning vehicle;

[0161] If not, determine the set of target cleaning areas of any cleaning vehicle, and the target cleaning set includes the initial area; repeatedly select the nearest area to be cleaned and add it to the set of target cleaning areas based on the set of target cleaning areas until the total cleaning task amount corresponding to the set of target cleaning areas is within the preset range, take the areas to be cleaned in the set of target cleaning areas as the target cleaning areas of any cleaning vehicle, and delete the target cleaning areas of any cleaning vehicle from all the areas to be cleaned.

[0162] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0163] For any cleaning vehicle, determine the current position of any cleaning vehicle and use it as the cleaning starting point; determine the positions of each target garbage included in the target cleaning area of any cleaning vehicle;

[0164] Take the position of the target garbage that is the farthest from any cleaning vehicle as the cleaning end point of any cleaning vehicle, take the positions of the remaining target garbage as cleaning points, and take the intersections in the map information as gathering points;

[0165] Traverse the cleaning starting point, gathering points, cleaning points and cleaning end point to obtain all paths for any cleaning vehicle to reach the cleaning end point from the cleaning starting point, and take the path with the shortest distance among all the paths as the cleaning path of any cleaning vehicle.

[0166] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0167] According to the cleaning path of each cleaning vehicle, generate a driving control signal for each cleaning vehicle correspondingly, and send the driving control signal of each cleaning vehicle to the corresponding cleaning vehicle. The driving control signal is used to instruct the cleaning vehicle to reach the target cleaning area and clean the garbage.

[0168] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0169] Obtain the current image captured by each binocular camera at the current moment;

[0170] Based on each current image, determine whether there is still garbage in each target cleaning area; if there is, determine the cleaning path of the target cleaning vehicle according to the map information of the target area and the target cleaning area with garbage, and send it to the corresponding target cleaning vehicle.

[0171] In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0172] Obtain the images captured by each binocular camera;

[0173] Based on each image, determine whether the area corresponding to each image is an area to be cleaned;

[0174] Based on the image corresponding to each area to be cleaned, determine the cleaning task amount of each cleaning vehicle in the target area;

[0175] Based on the cleaning task amount of each cleaning vehicle, determine the target cleaning area of each cleaning vehicle;

[0176] Based on the map information of the target area and the target cleaning area of each cleaning vehicle, determine the cleaning path of each cleaning vehicle, and send it to the corresponding cleaning vehicle.

[0177] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0178] Input each image into a first preset model, and output the number of garbage corresponding to each image;

[0179] Determine whether the number of garbage corresponding to each image is greater than a preset threshold, and list the area corresponding to the image with the number of garbage greater than the preset threshold as an area to be cleaned.

[0180] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0181] Take the area to be cleaned corresponding to any image among all areas to be cleaned as the initial area;

[0182] For any cleaning vehicle, determine whether the cleaning task amount corresponding to the initial area is within a preset range; the preset range is determined according to the cleaning task amount of any cleaning vehicle; if it is, take the initial area as the target cleaning area of any cleaning vehicle;

[0183] If not, determine the set of target cleaning areas for any cleaning vehicle. The target cleaning set includes the initial area. Based on the set of target cleaning areas, repeatedly select the nearest area to be cleaned and add it to the set of target cleaning areas until the total cleaning task volume corresponding to the set of target cleaning areas is within the preset range. Take the areas to be cleaned in the set of target cleaning areas as the target cleaning areas for any cleaning vehicle, and delete the target cleaning areas of any cleaning vehicle from all areas to be cleaned.

[0184] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0185] For any cleaning vehicle, determine the current position of any cleaning vehicle and use it as the cleaning starting point. Determine the positions of each target garbage included in the target cleaning area of any cleaning vehicle.

[0186] Take the position of the target garbage that is farthest from any cleaning vehicle as the cleaning end point of any cleaning vehicle, take the positions of the remaining target garbage as cleaning points, and take the intersections in the map information as gathering points.

[0187] Traverse the cleaning starting point, gathering points, cleaning points, and cleaning end point to obtain all paths for any cleaning vehicle to reach the cleaning end point from the cleaning starting point. Take the path with the shortest distance among all paths as the cleaning path of any cleaning vehicle.

[0188] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0189] According to the cleaning path of each cleaning vehicle, generate the driving control signal of each cleaning vehicle correspondingly, and send the driving control signal of each cleaning vehicle to the corresponding cleaning vehicle. The driving control signal is used to instruct the cleaning vehicle to reach the target cleaning area and clean the garbage.

[0190] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0191] Obtain the current images captured by each binocular camera at the current moment.

[0192] According to each current image, determine whether there is still garbage in each target cleaning area. If so, determine the cleaning path of the target cleaning vehicle according to the map information of the target area and the target cleaning area where there is garbage, and send it to the corresponding target cleaning vehicle.

[0193] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0194] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0195] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. A sweeper scheduling method, characterized in that, There are multiple binocular cameras set in the target area, and the method includes: Obtain the images captured by each binocular camera; Determine whether the area corresponding to each image is an area to be cleaned according to each image; Determine the cleaning task amount of each cleaning vehicle in the target area according to the image corresponding to each area to be cleaned; Take the area to be cleaned corresponding to any one of the images in all the areas to be cleaned as the initial area; For any cleaning vehicle, determine whether the cleaning task amount corresponding to the initial area is within a preset range; the preset range is determined according to the cleaning task amount of the any cleaning vehicle; if it is, take the initial area as the target cleaning area of the any cleaning vehicle; If not, determine the set of target cleaning areas of the any cleaning vehicle, and the target cleaning set includes the initial area; repeatedly select the nearest area to be cleaned based on the set of target cleaning areas and add it to the set of target cleaning areas until the total cleaning task amount corresponding to the set of target cleaning areas is within the preset range, take the areas to be cleaned in the set of target cleaning areas as the target cleaning areas of the any cleaning vehicle, and delete the target cleaning areas of the any cleaning vehicle from all the areas to be cleaned; Determine the cleaning path of each cleaning vehicle according to the map information of the target area and the target cleaning area of each cleaning vehicle, and send it to the corresponding cleaning vehicle.

2. The method according to claim 1, wherein The determining whether the area corresponding to each image is an area to be cleaned according to each image includes: Input each image into a first preset model, and output the number of garbage corresponding to each image; Determine whether the number of garbage corresponding to each image is greater than a preset threshold, and list the area corresponding to the image with the number of garbage greater than the preset threshold as the area to be cleaned.

3. The method according to claim 1, wherein The determining the cleaning path of each cleaning vehicle according to the map information of the target area and the target cleaning area of each cleaning vehicle includes: For any cleaning vehicle, determine the current position of the any cleaning vehicle and use it as the cleaning starting point; determine the positions of each target garbage included in the target cleaning area of the any cleaning vehicle; Take the position of the target garbage farthest from the any cleaning vehicle as the cleaning end point of the any cleaning vehicle, take the positions of the remaining target garbage as cleaning points, and take the intersections in the map information as gathering points; Traverse the cleaning starting point, gathering points, cleaning points and the cleaning end point, obtain all the paths for the any cleaning vehicle to reach the cleaning end point from the cleaning starting point, and take the path with the shortest distance among all the paths as the cleaning path of the any cleaning vehicle.

4. The method according to claim 1, characterized in that, The method further includes: Generate a driving control signal corresponding to each cleaning vehicle according to the cleaning path of each cleaning vehicle, and send the driving control signal of each cleaning vehicle to the corresponding cleaning vehicle. The driving control signal is used to instruct the cleaning vehicle to reach the target cleaning area and clean the garbage.

5. The method according to claim 1, wherein The method further includes: Obtain the current image captured by each binocular camera at the current moment; Based on each current image, determine whether there is still garbage in each target cleaning area; if so, determine the cleaning path of the target cleaning vehicle according to the map information of the target area and the target cleaning area with garbage, and send it to the corresponding target cleaning vehicle.

6. A sweeper scheduling device, characterized in that, The device includes: A first acquisition module, configured to acquire the images captured by each binocular camera; A first determination module, configured to determine, according to each image, whether the area corresponding to each image is an area to be cleaned; A second determination module, configured to determine the cleaning task amount of each cleaning vehicle in the target area according to the image corresponding to each area to be cleaned; A third determination module, configured to use the area to be cleaned corresponding to any one of the images in all the areas to be cleaned as the initial area; For any cleaning vehicle, determine whether the cleaning task amount corresponding to the initial area is within a preset range; the preset range is determined according to the cleaning task amount of the any cleaning vehicle; if so, use the initial area as the target cleaning area of the any cleaning vehicle; If not, determine the set of target cleaning areas of the any cleaning vehicle, and the target cleaning set includes the initial area; based on the set of target cleaning areas, repeatedly select the nearest area to be cleaned and add it to the set of target cleaning areas until the total cleaning task amount corresponding to the set of target cleaning areas is within the preset range, use the areas to be cleaned in the set of target cleaning areas as the target cleaning areas of the any cleaning vehicle, and delete the target cleaning areas of the any cleaning vehicle from all the areas to be cleaned; A fourth determination module, configured to determine the cleaning path of each cleaning vehicle according to the map information of the target area and the target cleaning area of each cleaning vehicle, and send it to the corresponding cleaning vehicle.

7. The device according to claim 6, characterized in that, The first determination module includes: An output unit, configured to input each image into a first preset model and output the garbage quantity corresponding to each image; A first determination unit, configured to determine whether the garbage quantity corresponding to each image is greater than a preset threshold, and list the area corresponding to the image with the garbage quantity greater than the preset threshold as the area to be cleaned.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images